forked from Archives/langchain
You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
38 lines
1.3 KiB
Python
38 lines
1.3 KiB
Python
from typing import List, Type
|
|
|
|
from pydantic import BaseModel, Extra, Field
|
|
|
|
from langchain.document_loaders.base import BaseLoader
|
|
from langchain.embeddings.base import Embeddings
|
|
from langchain.embeddings.openai import OpenAIEmbeddings
|
|
from langchain.text_splitter import RecursiveCharacterTextSplitter, TextSplitter
|
|
from langchain.vectorstores.base import VectorStore
|
|
from langchain.vectorstores.chroma import Chroma
|
|
|
|
|
|
def _get_default_text_splitter() -> TextSplitter:
|
|
return RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
|
|
|
|
|
|
class VectorstoreIndexCreator(BaseModel):
|
|
"""Logic for creating indexes."""
|
|
|
|
vectorstore_cls: Type[VectorStore] = Chroma
|
|
embedding: Embeddings = Field(default_factory=OpenAIEmbeddings)
|
|
text_splitter: TextSplitter = Field(default_factory=_get_default_text_splitter)
|
|
|
|
class Config:
|
|
"""Configuration for this pydantic object."""
|
|
|
|
extra = Extra.forbid
|
|
arbitrary_types_allowed = True
|
|
|
|
def from_loaders(self, loaders: List[BaseLoader]) -> VectorStore:
|
|
"""Create a vectorstore index from loaders."""
|
|
docs = []
|
|
for loader in loaders:
|
|
docs.extend(loader.load())
|
|
sub_docs = self.text_splitter.split_documents(docs)
|
|
vectorstore = self.vectorstore_cls.from_documents(sub_docs, self.embedding)
|
|
return vectorstore
|